
# !pip install -q datascience                                                       # Package that is required by pandas profiling
# !pip install -q pandas-profiling


# !pip install -q --upgrade pandas-profiling


#-------------------------------------------------------------------------------------------------------------------------------
import pandas as pd                                                 # Importing for panel data analysis
from pandas_profiling import ProfileReport                          # Import Pandas Profiling (To generate Univariate Analysis) 
#-------------------------------------------------------------------------------------------------------------------------------
import numpy as np                                                  # Importing package numpys (For Numerical Python)
#-------------------------------------------------------------------------------------------------------------------------------
import plotly.express as px
import matplotlib.pyplot as plt                                     # Importing pyplot interface using matplotlib
import seaborn as sns                                               # Importin seaborm library for interactive visualization
%matplotlib inline
#-------------------------------------------------------------------------------------------------------------------------------
from sklearn.linear_model import LinearRegression                   # Importing Linear Regression model
from sklearn.metrics import mean_squared_error                      # To calculate the MSE of a regression model
from sklearn.metrics import mean_absolute_error                     # To calculate the MAE of a regression model
from sklearn.metrics import r2_score                                # To calculate the R-squared score of a regression model
from sklearn.model_selection import train_test_split                # To split the data in training and testing part
from sklearn.preprocessing import StandardScaler                    # Importing Standard Scaler library from preprocessing
from sklearn.preprocessing import LabelEncoder                      # Importing Label Encoder library from preprocessing
#-------------------------------------------------------------------------------------------------------------------------------
import folium                                                       # Importing folium package
from folium import Map, Marker                                      # Importing folium to plot locations on map
#-------------------------------------------------------------------------------------------------------------------------------
import warnings                                                     # Importing warning to disable runtime warnings
warnings.filterwarnings('ignore')                                   # Warnings will appear only once


HomeSweetHome = pd.read_csv('C:/Users/Mahesh/Downloads/Python/Term Projects/ML_Intermediate/rentel price/train_data.csv')
print('Data Shape:', HomeSweetHome.shape)
HomeSweetHome.head()

Data Shape: (137023, 17)


HomeSweetHome.columns

Index(['id', 'name', 'host_id', 'host_name', 'neighbourhood_group',
       'neighbourhood', 'latitude', 'longitude', 'room_type', 'minimum_nights',
       'number_of_reviews', 'last_review', 'reviews_per_month',
       'calculated_host_listings_count', 'availability_365', 'city', 'price'],
      dtype='object')


HomeSweetHome.describe(include='all')


HomeSweetHome.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 137023 entries, 0 to 137022
Data columns (total 17 columns):
 #   Column                          Non-Null Count   Dtype  
---  ------                          --------------   -----  
 0   id                              137023 non-null  int64  
 1   name                            137007 non-null  object 
 2   host_id                         137023 non-null  float64
 3   host_name                       137002 non-null  object 
 4   neighbourhood_group             80300 non-null   object 
 5   neighbourhood                   137023 non-null  object 
 6   latitude                        137023 non-null  float64
 7   longitude                       137023 non-null  float64
 8   room_type                       137023 non-null  object 
 9   minimum_nights                  137023 non-null  float64
 10  number_of_reviews               137023 non-null  float64
 11  last_review                     107232 non-null  object 
 12  reviews_per_month               107232 non-null  float64
 13  calculated_host_listings_count  137023 non-null  float64
 14  availability_365                137023 non-null  float64
 15  city                            137023 non-null  object 
 16  price                           137023 non-null  float64
dtypes: float64(9), int64(1), object(7)
memory usage: 17.8+ MB


# profile = ProfileReport(rental_df, title="Rental Profiling Report")
# profile.to_file("Rental_report.html")
# print('Accomplished!')


HomeSweetHome.isna().sum()

id                                    0
name                                 16
host_id                               0
host_name                            21
neighbourhood_group               56723
neighbourhood                         0
latitude                              0
longitude                             0
room_type                             0
minimum_nights                        0
number_of_reviews                     0
last_review                       29791
reviews_per_month                 29791
calculated_host_listings_count        0
availability_365                      0
city                                  0
price                                 0
dtype: int64


# lets check data for Nul values in 'reviews_per_month'

HomeSweetHome[HomeSweetHome['reviews_per_month'].isna()]


HomeSweetHome[HomeSweetHome['neighbourhood_group'].isna()]['city'].value_counts()

Broward County    8773
Austin            8432
Clark County      6718
New Orleans       5117
Chicago           5052
Nashville         4892
Portland          3448
Denver            3347
Boston            2663
Oakland           2555
Jersey City       2000
Asheville         1641
Columbus          1112
Cambridge          828
Pacific Grove      145
Name: city, dtype: int64


HomeSweetHome["neighbourhood_group"].value_counts(dropna=False)

NaN                     56723
Manhattan               16096
Brooklyn                14615
City of Los Angeles     14092
Other Cities             9126
Maui                     6361
Honolulu                 5025
Queens                   4584
Hawaii                   3990
Kauai                    2588
Unincorporated Areas     2035
Bronx                     962
Newport                   264
Staten Island             262
Washington                139
Providence                122
Kent                       22
Bristol                    17
Name: neighbourhood_group, dtype: int64


HomeSweetHome["reviews_per_month"].fillna(value=0, inplace=True)
HomeSweetHome["neighbourhood_group"]=np.where(HomeSweetHome["neighbourhood_group"].isnull(),HomeSweetHome['city'],HomeSweetHome["neighbourhood_group"])


print(HomeSweetHome.shape)

(137023, 17)


HomeSweetHome[HomeSweetHome.duplicated()]


HomeSweetHome.city.value_counts()

New York City     36519
Los Angeles       25253
Hawaii            17964
Broward County     8773
Austin             8432
Clark County       6718
New Orleans        5117
Chicago            5052
Nashville          4892
Portland           3448
Denver             3347
Boston             2663
Oakland            2555
Jersey City        2000
Asheville          1641
Columbus           1112
Cambridge           828
Rhode Island        564
Pacific Grove       145
Name: city, dtype: int64


# to check distribution of 'neighbourhood_group'

px.histogram(HomeSweetHome, x= 'neighbourhood_group', marginal='box',
                nbins=47, title='Distribution of neighbourhood_group')


# to check distribution of 'room_type'

px.histogram(HomeSweetHome, x= 'room_type', marginal='box',
                nbins=47, title='Distribution of room_type')


# to check distribution of 'minimum_nights'

plt.figure(figsize=(15,3))
sns.distplot(HomeSweetHome['minimum_nights'])

<AxesSubplot:xlabel='minimum_nights', ylabel='Density'>


# to check distribution of 'number_of_reviews'

plt.figure(figsize=(15,3))
sns.distplot(HomeSweetHome['number_of_reviews'])

<AxesSubplot:xlabel='number_of_reviews', ylabel='Density'>


# to check distribution of 'calculated_host_listings_count'

plt.figure(figsize=(15,3))
sns.distplot(HomeSweetHome['calculated_host_listings_count'])

<AxesSubplot:xlabel='calculated_host_listings_count', ylabel='Density'>


# to check distribution of 'availability_365'

plt.figure(figsize=(15,3))
sns.distplot(HomeSweetHome['availability_365'])

<AxesSubplot:xlabel='availability_365', ylabel='Density'>


px.histogram(HomeSweetHome, x= 'availability_365', marginal='box',
                nbins=47, title='Distribution of availability_365')


px.histogram(HomeSweetHome, x= 'price', marginal='box',
                nbins=47, title='Distribution of price')


px.histogram(HomeSweetHome[HomeSweetHome['price']<1000], x= 'price', marginal='box',
                nbins=47, title='Distribution of price')


px.scatter(HomeSweetHome,x='number_of_reviews',y='reviews_per_month')


px.scatter(HomeSweetHome,x='calculated_host_listings_count',y='price')


px.scatter(HomeSweetHome,y='calculated_host_listings_count',x='availability_365')


px.scatter(HomeSweetHome,x='reviews_per_month',y='price')


plt.figure(figsize=(6,4))
sns.barplot(data=HomeSweetHome,x='room_type',y='price')

<AxesSubplot:xlabel='room_type', ylabel='price'>


plt.figure(figsize=(8,8))
sns.heatmap(HomeSweetHome.corr(),annot=True,cmap='icefire')

<AxesSubplot:>


HomeSweetHome.skew()

id                                 0.001497
host_id                            1.051471
latitude                          -0.725820
longitude                         -0.740660
minimum_nights                    15.694661
number_of_reviews                  3.702934
reviews_per_month                  2.677926
calculated_host_listings_count     6.388123
availability_365                   0.182854
price                             20.790929
dtype: float64


HomeSweetHome.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 137023 entries, 0 to 137022
Data columns (total 17 columns):
 #   Column                          Non-Null Count   Dtype  
---  ------                          --------------   -----  
 0   id                              137023 non-null  int64  
 1   name                            137007 non-null  object 
 2   host_id                         137023 non-null  float64
 3   host_name                       137002 non-null  object 
 4   neighbourhood_group             137023 non-null  object 
 5   neighbourhood                   137023 non-null  object 
 6   latitude                        137023 non-null  float64
 7   longitude                       137023 non-null  float64
 8   room_type                       137023 non-null  object 
 9   minimum_nights                  137023 non-null  float64
 10  number_of_reviews               137023 non-null  float64
 11  last_review                     107232 non-null  object 
 12  reviews_per_month               137023 non-null  float64
 13  calculated_host_listings_count  137023 non-null  float64
 14  availability_365                137023 non-null  float64
 15  city                            137023 non-null  object 
 16  price                           137023 non-null  float64
dtypes: float64(9), int64(1), object(7)
memory usage: 17.8+ MB


HomeSweetHome_copy=HomeSweetHome.copy()


HomeSweetHome_copy[['minimum_nights','number_of_reviews','reviews_per_month','calculated_host_listings_count',
                   'availability_365','price']]=HomeSweetHome_copy[['minimum_nights','number_of_reviews','reviews_per_month','calculated_host_listings_count',
                   'availability_365','price']].astype('int')


HomeSweetHome_copy.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 137023 entries, 0 to 137022
Data columns (total 17 columns):
 #   Column                          Non-Null Count   Dtype  
---  ------                          --------------   -----  
 0   id                              137023 non-null  int64  
 1   name                            137007 non-null  object 
 2   host_id                         137023 non-null  float64
 3   host_name                       137002 non-null  object 
 4   neighbourhood_group             137023 non-null  object 
 5   neighbourhood                   137023 non-null  object 
 6   latitude                        137023 non-null  float64
 7   longitude                       137023 non-null  float64
 8   room_type                       137023 non-null  object 
 9   minimum_nights                  137023 non-null  int32  
 10  number_of_reviews               137023 non-null  int32  
 11  last_review                     107232 non-null  object 
 12  reviews_per_month               137023 non-null  int32  
 13  calculated_host_listings_count  137023 non-null  int32  
 14  availability_365                137023 non-null  int32  
 15  city                            137023 non-null  object 
 16  price                           137023 non-null  int32  
dtypes: float64(3), int32(6), int64(1), object(7)
memory usage: 14.6+ MB


#Filtering the data without 0 Values in Price

HomeSweetHome_copy=HomeSweetHome_copy[HomeSweetHome_copy['price']>0]


HomeSweetHome_copy.shape

(136981, 17)


HomeSweetHome_copy=HomeSweetHome_copy[HomeSweetHome_copy['price']<400]
HomeSweetHome_copy.shape

(125699, 17)


df_cont = HomeSweetHome_copy.select_dtypes(exclude='object')

df_cat = HomeSweetHome_copy.select_dtypes(include='object')


df_cat.head()


df_cont.head()


# 'name', 'host_name', 'neighbourhood', 'last_review' can be dropped from Categorical df
df_cat=df_cat.drop(['name', 'host_name', 'neighbourhood', 'last_review'], axis=1)

# 'id','host_id','reviews_per_month' can be dropped from Continuous df
df_cont=df_cont.drop(['id','host_id','reviews_per_month'],axis=1)


df_cont.head()


df_cat.head()


df_cat = df_cat.apply(LabelEncoder().fit_transform)
df_cat.head()


df_comb=pd.concat([df_cat, df_cont], axis = 1)
df_comb.head()


df_comb.skew()

neighbourhood_group                0.229196
room_type                          0.788885
city                              -0.685629
latitude                          -0.786414
longitude                         -0.775323
minimum_nights                    15.289802
number_of_reviews                  3.601265
calculated_host_listings_count     6.702582
availability_365                   0.222720
price                              1.081080
dtype: float64


def seperate_Xy(data=None):
    X = data.drop(labels=['price'], axis=1)
    y = data['price']
    return X, y


X, y = seperate_Xy(data=df_comb)
X.head()


y.head()

0    100
1    102
2    131
4     76
5     59
Name: price, dtype: int32


scaler = StandardScaler() 
scaler.fit(X) 

X = pd.DataFrame(scaler.transform(X), index = X.index, columns = X.columns + '_S')


X.head()


y = np.log(y)
y.head()

0    4.605170
1    4.624973
2    4.875197
4    4.330733
5    4.077537
Name: price, dtype: float64


X.skew()

neighbourhood_group_S                0.229196
room_type_S                          0.788885
city_S                              -0.685629
latitude_S                          -0.786414
longitude_S                         -0.775323
minimum_nights_S                    15.289802
number_of_reviews_S                  3.601265
calculated_host_listings_count_S     6.702582
availability_365_S                   0.222720
dtype: float64


def Xy_splitter(X=None, y=None):
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 42)
    print('Training Data Shape:', X_train.shape, y_train.shape)
    print('Testing Data Shape:', X_test.shape, y_test.shape)
    return X_train, X_test, y_train, y_test


X_train, X_test, y_train, y_test = Xy_splitter(X=X, y=y)

Training Data Shape: (94274, 9) (94274,)
Testing Data Shape: (31425, 9) (31425,)


def model_generator_lr():
    return LinearRegression()


clf = model_generator_lr()


def train_n_eval(clf=None):
    
    # Extracting model name
    model_name = type(clf).__name__
    
    # Fit the model on train data
    clf.fit(X_train, y_train)
    
    # Make predictions using test data
    y_pred = clf.predict(X_test)
    
    # Make predictions using test data
    y_pred_train = clf.predict(X_train)
    
    # Calculate test accuracy of the model
    clf_mae = mean_absolute_error(y_test, y_pred)
    
    # Calculate train accuracy of the model
    clf_mae_train = mean_absolute_error(y_train, y_pred_train)
    
    # Calculate test accuracy of the model
    clf_mse = mean_squared_error(y_test, y_pred)
    
    # Calculate train accuracy of the model
    clf_mse_train = mean_squared_error(y_train, y_pred_train)
    
    # Calculate test accuracy of the model
    clf_r2 = r2_score(y_test, y_pred)
    
    # Calculate train accuracy of the model
    clf_r2_train = r2_score(y_train, y_pred_train)
    
    # Display the accuracy of the model
    print('Performance Metrics for', model_name, ':\n')
    print('[Mean Absolute Error Train]:', clf_mae_train)
    print('[Mean Absolute Error Test]:', clf_mae, ':\n')
    print('*******************************\n')
    print('[Mean Sqaured Error Train]:', clf_mse_train)
    print('[Mean Sqaured Error Test]:', clf_mse, ':\n')
    print('*******************************\n')
    print('[Root Mean Sqaured Error Train]:', np.sqrt(clf_mse_train))
    print('[Root Mean Sqaured Error Test]:', np.sqrt(clf_mse), ':\n')
    print('*******************************\n')
    print('[R2-Score Train]:', clf_r2_train)
    print('[R2-Score Test]:', clf_r2)


train_n_eval(clf=clf)

Performance Metrics for LinearRegression :

[Mean Absolute Error Train]: 0.40754035769661023
[Mean Absolute Error Test]: 0.4048206163822222 :

*******************************

[Mean Sqaured Error Train]: 0.25813454531286567
[Mean Sqaured Error Test]: 0.25564061718755987 :

*******************************

[Root Mean Sqaured Error Train]: 0.5080694296184978
[Root Mean Sqaured Error Test]: 0.5056091545725412 :

*******************************

[R2-Score Train]: 0.35258113777827904
[R2-Score Test]: 0.3548097878310106


df_test=pd.read_csv('C:/Users/Mahesh/Downloads/Python/Term Projects/ML_Intermediate/rentel price/test_data.csv')
df_test.head()


df_test["reviews_per_month"].fillna(value=0, inplace=True)
df_test["neighbourhood_group"]=np.where(df_test["neighbourhood_group"].isnull(),df_test['city'],df_test["neighbourhood_group"])

df_test[['minimum_nights','number_of_reviews','reviews_per_month','calculated_host_listings_count',
                   'availability_365']]=df_test[['minimum_nights','number_of_reviews','reviews_per_month','calculated_host_listings_count',
                   'availability_365']].astype('int')
                   
df_test_cont = df_test.select_dtypes(exclude='object')

df_test_cat = df_test.select_dtypes(include='object')

df_test_cat=df_test_cat.drop(['name', 'host_name', 'neighbourhood', 'last_review'], axis=1)

df_test_cont=df_test_cont.drop(['id','host_id','reviews_per_month'],axis=1)


df_test_cat = df_test_cat.apply(LabelEncoder().fit_transform)

df_test_comb=pd.concat([df_test_cat, df_test_cont], axis = 1)

scaler.fit(df_test_comb) 

df_test_comb = pd.DataFrame(scaler.transform(df_test_comb), index = df_test_comb.index, columns = df_test_comb.columns + '_S')


df_test.head()


# Make predictions using test data
y_test_pred = clf.predict(df_test_comb)
print(np.round(np.exp(y_test_pred),decimals=0))

[151. 133. 147. ...  71. 138. 161.]


index=df_test['id']
result=pd.DataFrame(np.round(np.exp(y_test_pred),decimals=0),index=index)


result.to_csv('C:/Users/Mahesh/Downloads/Python/Term Projects/ML_Intermediate/rentel price/result.csv', header=False)
print("Successful")

Successful


result

	id	name	host_id	host_name	neighbourhood_group	neighbourhood	latitude	longitude	room_type	minimum_nights	number_of_reviews	last_review	reviews_per_month	calculated_host_listings_count	availability_365	city	price
0	149653	Private bedroom located in Downtown Manhattan	257599351.0	Sandra And Katharina	Manhattan	Chinatown	40.71703	-73.99538	Private room	2.0	17.0	18/09/19	1.04	1.0	0.0	New York City	100.0
1	74702	Quiet, Comfy West LA Cottage - HSR 19-000047	2882551.0	James	City of Los Angeles	Mar Vista	34.01257	-118.44254	Entire home/apt	2.0	331.0	07/09/20	4.28	1.0	170.0	Los Angeles	102.0
2	95858	Home away from Home !	287662307.0	Kahee	Other Cities	Pasadena	34.14255	-118.09888	Entire home/apt	10.0	4.0	29/03/20	0.37	1.0	306.0	Los Angeles	131.0
3	61301	Kukui‚Äôula Club Villa 11	198477445.0	Lodge	Kauai	Koloa-Poipu	21.88471	-159.48359	Entire home/apt	1.0	0.0	NaN	NaN	19.0	358.0	Hawaii	2399.0
4	132101	One bedroom apartment	87835557.0	Kostas	Queens	Astoria	40.76623	-73.90911	Entire home/apt	2.0	189.0	31/08/20	3.82	1.0	331.0	New York City	76.0

Column Name	Description
host_id	unique host Id
host_name	name of the host
neighbourhood_group	group in which the neighbourhood lies
neighbourhood	name of the neighbourhood
latitude	latitude of listing
longitude	longitude of listing
room_type	type of room
minimum_nights	minimum no. of nights required to book.
number_of_reviews	total number of reviews on the listing
last_review	the date on which listing received its last review
reviews_per_month	average reviews per month on listing
calculated_host_listings_count	total number of listings by host
availability_365	number of days in the year the listing is available for rent
city	region of the listing
price	price of listing per night

Observations	Values
Number of columns	17
Number of rows	137023
Missing cells	116342
Duplicate rows	0
Continuous type columns	10
Categorical type columns	7

	id	name	host_id	host_name	neighbourhood_group	neighbourhood	latitude	longitude	room_type	minimum_nights	number_of_reviews	last_review	reviews_per_month	calculated_host_listings_count	availability_365	city	price
3	61301	Kukui‚Äôula Club Villa 11	198477445.0	Lodge	Kauai	Koloa-Poipu	21.88471	-159.48359	Entire home/apt	1.0	0.0	NaN	NaN	19.0	358.0	Hawaii	2399.0
8	47667	Beautiful, unique 3 bedroom, 3.5 bath home loc...	225117269.0	Hank	NaN	Highland	39.75848	-105.01377	Entire home/apt	3.0	0.0	NaN	NaN	1.0	336.0	Denver	299.0
11	159356	Cozy Room at Roosvelt Island - Full Bed	16909509.0	Lu	Manhattan	Roosevelt Island	40.76440	-73.94666	Private room	5.0	0.0	NaN	NaN	1.0	0.0	New York City	70.0
13	88622	Venue/ Hall / Party	85868649.0	Event Space	Other Cities	Glendale	34.14309	-118.26325	Entire home/apt	1.0	0.0	NaN	NaN	2.0	364.0	Los Angeles	700.0
16	159582	OVERSIZED SUN-FLOODED STUDIO IN SUGAR HILL	24583865.0	Rebecca	Manhattan	Harlem	40.82749	-73.94484	Entire home/apt	30.0	0.0	NaN	NaN	1.0	0.0	New York City	95.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
136999	130608	Private 2bdr apt. awesome LES/Chinatown location	6917811.0	Gia	Manhattan	Civic Center	40.71537	-74.00181	Private room	2.0	0.0	NaN	NaN	1.0	0.0	New York City	130.0
137008	67221	Christmas In Maui!	18397245.0	Sherri	Maui	Kihei-Makena	20.68676	-156.43680	Entire home/apt	4.0	0.0	NaN	NaN	1.0	0.0	Hawaii	550.0
137010	16023	The Red Cottage	10907013.0	Samantha	NaN	Fort Lauderdale	26.11271	-80.16019	Private room	1.0	0.0	NaN	NaN	1.0	365.0	Broward County	150.0
137017	110268	Music City Villa in East Nashville sleeps 10	35100052.0	Victor	NaN	District 7	36.20469	-86.73784	Entire home/apt	2.0	0.0	NaN	NaN	4.0	337.0	Nashville	259.0
137019	103694	FANTASTIC 2BR/2BA! POOL, CLOSE TO ATTRACTIONS	174792040.0	RoomPicks By Victoria	City of Los Angeles	Downtown	34.04472	-118.25665	Private room	1.0	0.0	NaN	NaN	14.0	91.0	Los Angeles	464.0

	name	host_name	neighbourhood_group	neighbourhood	room_type	last_review	city
0	Private bedroom located in Downtown Manhattan	Sandra And Katharina	Manhattan	Chinatown	Private room	18/09/19	New York City
1	Quiet, Comfy West LA Cottage - HSR 19-000047	James	City of Los Angeles	Mar Vista	Entire home/apt	07/09/20	Los Angeles
2	Home away from Home !	Kahee	Other Cities	Pasadena	Entire home/apt	29/03/20	Los Angeles
4	One bedroom apartment	Kostas	Queens	Astoria	Entire home/apt	31/08/20	New York City
5	10th St Renovated Beauty- Rm 3U	Scott	Oakland	Prescott	Private room	31/05/19	Oakland

Linear Regression (Term project)

Table of Contents¶

1. Introduction¶

2. Problem Statement¶

3. Installing & Importing Libraries¶

3.1 Installing Libraries¶

3.2 Upgrading Libraries¶

3.3 Importing Libraries¶

4. Data Acquisition & Description¶

4.1 Data Description¶

4.2 Data Information¶

5. Data Pre-Processing¶

5.1 Pre Profiling Report¶

Observations from Profile Report

B. Missing Data from below variables:

C. Below are unique values:

6. Exploratory Data Analysis¶

6.1 Univariate Analysis¶

6.2 Bivariate analysis¶

6.3 Multivariate analysis¶

7. Data Post-Processing¶

7.1 Feature Extraction¶

7.2 Feature Transformation¶

7.3 Feature Independant & Dependant Separation¶

7.3 Feature Scaling¶

7.4 Data Preparation for Training & Testing¶

8. Model Development & Evaluation¶

Implementing Model on provided data¶

	id	name	host_id	host_name	neighbourhood_group	neighbourhood	latitude	longitude	room_type	minimum_nights	number_of_reviews	last_review	reviews_per_month	calculated_host_listings_count	availability_365	city	price
count	137023.000000	137007	1.370230e+05	137002	80300	137023	137023.000000	137023.000000	137023	137023.000000	137023.000000	107232	107232.000000	137023.000000	137023.000000	137023	137023.000000
unique	NaN	132769	NaN	21866	17	1134	NaN	NaN	4	NaN	NaN	2271	NaN	NaN	NaN	19	NaN
top	NaN	A place of your own \| 2BR in Las Vegas	NaN	Michael	Manhattan	Unincorporated Areas	NaN	NaN	Entire home/apt	NaN	NaN	15/03/20	NaN	NaN	NaN	New York City	NaN
freq	NaN	44	NaN	1228	16096	5222	NaN	NaN	93651	NaN	NaN	1858	NaN	NaN	NaN	36519	NaN
mean	85580.723397	NaN	9.632567e+07	NaN	NaN	NaN	34.584207	-101.510148	NaN	10.446071	33.138831	NaN	1.387220	17.226174	163.602446	NaN	205.281792
std	49471.662411	NaN	1.007056e+08	NaN	NaN	NaN	7.063332	28.013884	NaN	25.593436	61.903532	NaN	1.650963	52.670175	140.766748	NaN	504.573579
min	1.000000	NaN	2.300000e+01	NaN	NaN	NaN	18.920990	-159.714900	NaN	1.000000	0.000000	NaN	0.010000	1.000000	0.000000	NaN	0.000000
25%	42729.500000	NaN	1.431064e+07	NaN	NaN	NaN	30.249505	-118.365710	NaN	1.000000	1.000000	NaN	0.220000	1.000000	1.000000	NaN	75.000000
50%	85640.000000	NaN	5.274681e+07	NaN	NaN	NaN	36.058990	-90.105520	NaN	3.000000	7.000000	NaN	0.780000	2.000000	151.000000	NaN	120.000000
75%	128374.500000	NaN	1.543914e+08	NaN	NaN	NaN	40.718400	-73.989320	NaN	7.000000	37.000000	NaN	2.000000	7.000000	316.000000	NaN	200.000000
max	171279.000000	NaN	3.679071e+08	NaN	NaN	NaN	45.617270	-70.995950	NaN	1250.000000	966.000000	NaN	44.060000	593.000000	365.000000	NaN	24999.000000

	neighbourhood_group_S	room_type_S	city_S	latitude_S	longitude_S	minimum_nights_S	number_of_reviews_S	calculated_host_listings_count_S	availability_365_S
0	0.582539	1.354976	0.913594	0.838742	0.963337	-0.338781	-0.280974	-0.294627	-1.140292
1	-0.543619	-0.701633	0.236777	-0.124875	-0.648639	-0.338781	4.648905	-0.294627	0.069343
2	1.333311	-0.701633	0.236777	-0.106193	-0.636175	-0.022619	-0.485077	-0.294627	1.037052
4	1.833826	-0.701633	0.913594	0.845813	0.966466	-0.338781	2.419469	-0.294627	1.214939
5	1.208182	1.354976	1.139199	0.421000	-0.788463	-0.141180	-0.296674	-0.218766	-1.140292

	id	name	host_id	host_name	neighbourhood_group	neighbourhood	latitude	longitude	room_type	minimum_nights	number_of_reviews	last_review	reviews_per_month	calculated_host_listings_count	availability_365	city
0	49653	Beachfront Bungalow & Home of Honu	24843776.0	Marco	Maui	Lahaina	20.95924	-156.68334	Entire home/apt	3.0	79.0	25/03/20	1.18	1.0	275.0	Hawaii
1	128272	Resort-like living in Williamsburg	14461742.0	Mohammed	Brooklyn	Williamsburg	40.71552	-73.93869	Entire home/apt	5.0	1.0	01/01/16	0.02	1.0	0.0	New York City
2	88753	Los Angeles Luxury Apartment in Downtown LA	205959517.0	Christian	City of Los Angeles	Downtown	34.04331	-118.25804	Entire home/apt	30.0	0.0	NaN	NaN	1.0	354.0	Los Angeles
3	151475	E Z Living In Harlem 2	244536777.0	Chester	Manhattan	Harlem	40.81615	-73.94359	Entire home/apt	3.0	4.0	01/12/19	0.30	2.0	180.0	New York City
4	134525	Cozy, neat, spacious 2 BR apartment in East Ha...	2247818.0	Gonda	Manhattan	East Harlem	40.80268	-73.94051	Entire home/apt	10.0	33.0	13/03/20	0.77	1.0	10.0	New York City

	0
id
49653	151.0
128272	133.0
88753	147.0
151475	142.0
134525	130.0
...	...
161801	65.0
28466	134.0
165580	71.0
40826	138.0
49668	161.0